US6928370B2 - Health monitoring - Google Patents

Health monitoring Download PDF

Info

Publication number
US6928370B2
US6928370B2 US09/898,008 US89800801A US6928370B2 US 6928370 B2 US6928370 B2 US 6928370B2 US 89800801 A US89800801 A US 89800801A US 6928370 B2 US6928370 B2 US 6928370B2
Authority
US
United States
Prior art keywords
signature
condition
normal
present time
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime, expires
Application number
US09/898,008
Other languages
English (en)
Other versions
US20020040278A1 (en
Inventor
Paul Anuzis
Steve P. King
Dennis M. King
Lionel Tarassenko
Paul Hayton
Simukai Utete
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Rolls Royce PLC
Original Assignee
Oxford Biosignals Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Oxford Biosignals Ltd filed Critical Oxford Biosignals Ltd
Assigned to ROLLS-ROYCE PLC reassignment ROLLS-ROYCE PLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: HAYTON, PAUL, TARASSENKO, LIONEL, UTETE, SIMUKAI, ANUZIS, PAUL, KING, DENNIS M., KING, STEVE P.
Publication of US20020040278A1 publication Critical patent/US20020040278A1/en
Assigned to OXFORD BIOSIGNALS LIMITED reassignment OXFORD BIOSIGNALS LIMITED ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: ROLLS-ROYCE PLC
Application granted granted Critical
Publication of US6928370B2 publication Critical patent/US6928370B2/en
Assigned to OXFORD BIOSIGNALS LIMITED reassignment OXFORD BIOSIGNALS LIMITED CHANGE OF ADDRESS Assignors: OXFORD BIOSIGNALS LIMITED
Assigned to OPTIMIZED SYSTEMS AND SOLUTIONS LIMITED reassignment OPTIMIZED SYSTEMS AND SOLUTIONS LIMITED ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: OXFORD BIOSIGNALS LIMITED
Assigned to ROLLS-ROYCE CONTROLS AND DATA SERVICES LIMITED reassignment ROLLS-ROYCE CONTROLS AND DATA SERVICES LIMITED ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: OPTIMIZED SYSTEMS AND SOLUTIONS LIMITED
Assigned to ROLLS-ROYCE PLC reassignment ROLLS-ROYCE PLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: ROLLS-ROYCE CONTROLS AND DATA SERVICES LIMITED
Adjusted expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/46—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by spectral analysis, e.g. Fourier analysis or wavelet analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H1/00—Measuring characteristics of vibrations in solids by using direct conduction to the detector
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04—Analysing solids
    • G01N29/12—Analysing solids by measuring frequency or resonance of acoustic waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/4481—Neural networks
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2291/00—Indexing codes associated with group G01N29/00
    • G01N2291/01—Indexing codes associated with the measuring variable
    • G01N2291/012—Phase angle
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2291/00—Indexing codes associated with group G01N29/00
    • G01N2291/01—Indexing codes associated with the measuring variable
    • G01N2291/015—Attenuation, scattering
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2291/00—Indexing codes associated with group G01N29/00
    • G01N2291/26—Scanned objects
    • G01N2291/269—Various geometry objects
    • G01N2291/2693—Rotor or turbine parts

Definitions

  • This invention relates to methods and data processing systems for monitoring the health of a system.
  • the methods and data processing systems of the invention are particularly, although not necessarily exclusively, suitable for monitoring the health of power plant, including for example gas turbine, spark ignition and compression ignition internal combustion engines.
  • the health of a system can be considered a measure of the condition of a system against expected norms.
  • a healthy system is one whose condition closely matches expectations, whereas an unhealthy system is one whose condition differs from what would be expected, indicating for example deterioration of, or a possible problem with the system.
  • the ability to monitor the health of a system can therefore allow such deterioration and/or problems to be detected and, if necessary, addressed at an early stage.
  • U.S. Pat. No. 5,684,718 describes a non-real time system for monitoring the operation of an electric generator in which vibration and load data are combined to produce a single signal which is then compared with stored data representative of maximum acceptable combinations of the two parameters.
  • the system is an automated “look up table” which issues warnings when vibrations have exceeded acceptable limits.
  • the number of indicators that must be monitored to obtain a useful overall picture of the system's condition can be high. This in turn means that the task of analysing the complete series of indicators to determine the health of the engine is a complex one, typically requiring a skilled expert to analyse the data off-line.
  • a first aspect of the invention provides a method for monitoring the health of a system, comprising:
  • condition signature from a plurality of measured condition indicators acquired from the system
  • signature pertains to the values of a plurality of condition indicators merged or fused into a unit or quantity such as a set, vector or scalar.
  • the indicators may correspond to respective elements of the vector.
  • the magnitude of the scalar may be determined by a mathematical function which acts upon the indicator values.
  • the task of assessing the health of a system is greatly simplified.
  • the detection of an event amounts to an indication of a potential problem or an unhealthy system (i.e. a system condition that differs from what would normally be expected)
  • the monitoring of the health can be largely automated, removing, or at least minimising, the requirement for expert input during the monitoring process. This in turn means that it becomes feasible to continuously monitor the health of a system, and to provide useful information about the health of the system in real time during operation.
  • condition indicators that are combined to form the system condition signature include operational parameters, which in the case of a mechanical system may be speeds, pressures (e.g. gas pressures, oil pressures) and temperatures for example.
  • Other useful parameters may include what might be conventionally thought of as control or status parameters. For convenience, such parameters will be referred to using the single label of “performance parameters” in the following text.
  • the signature includes one or more condition indicators related to the vibration of the system.
  • condition indicators from which the system condition signature is constructed may be derived from two or more disparate sources of data. This illustrates a particular strength of this approach in that a great variety of different forms of condition indicator data can be encompassed in the system condition signature, providing a more comprehensive measure of the system's health than has previously been possible without multiple analyses.
  • condition indicators are used to construct the condition signature. More preferably at least 10 and even more preferably at least 20 condition indicators are used to construct the condition signature.
  • the system comprises a gas turbine engine.
  • the normal signature for the system can be derived from a predefined model of the system that is being monitored. This model can itself be developed off-line and then fixed for the duration of the operation of the health monitoring method. More preferably, however, the model is designed to be refined as the method proceeds in order that it might be better tuned to a specific system.
  • the model is a “learnt model” developed using a data-driven, or at least partially data-driven approach. That is to say the learnt model learns from training data comprising series of the condition indicators which have been labelled as normal (i.e. healthy) or abnormal (i.e. unhealthy) as the case may be. In fact, it is often the case that normal data is far more readily available than abnormal data and therefore the training data may only include examples of normal data. This still results in an effective model, because subsequent events can then be identified as departures from the learnt model of normality.
  • the normal signature for the healthy system may be predicted from a model defining one or more inter-dependencies between the condition indicators. This enables the model to specify a continuous boundary in N-dimensional space (where each dimension relates to one of N condition indicators) corresponding to the limits of healthy system operation. This is in contrast to “look up table” approaches for setting the limits of healthy system operation which do not capture the (often complex) inter-relationships and correlations between condition indicators.
  • condition signature for the healthy system is predicted from a model defining one or more inter-dependencies between the condition indicators the several small changes in the condition indicators may have the cumulative effect of driving the condition signature outside normal boundary in N-dimensional space.
  • the predetermined threshold corresponds to a statistically significant departure or variance from normality as defined by the normal signature.
  • the model e.g. due to the input of more training data
  • the invention provides a method for monitoring the health of a system, which comprises performing at each of a plurality of times the steps of:
  • condition signature from a plurality of condition indicators including (a) a plurality of vibration measurements acquired from the system or (b) one or more vibration measurements and one or more performance parameter measurements acquired from the system;
  • the model may comprise a matrix (e.g. a covariance matrix) with one or more non-zero off-diagonal terms to define the inter-dependencies.
  • the step of comparing the condition signature with the normal signature may then involve calculating a value for the normalised innovations squared (NIS) which is defined below in the “Description of the Embodiments”.
  • NIS normalised innovations squared
  • N1 condition indicators such as vibration values, e.g. at a number of key frequencies
  • the times define successive intervals of at most 1 sec duration (i.e. a 1 Hz repetition frequency). More preferably the times define successive intervals of at most 0.2 sec duration (a 5 Hz repetition frequency), even more preferably at most 0.1 sec (a 10 Hz repetition frequency).
  • the data acquisition rate can, however, be significantly faster than the processing rate.
  • the data acquisition rate may be in the range 20 Hz to 80 kHz. Only a subset of the acquired data may then be processed.
  • the invention provides a method for monitoring the health of a system, which comprises performing at each of a plurality of times defining successive intervals of at most 1 sec duration the steps of:
  • condition signature from a plurality of condition indicators including (a) a plurality of vibration measurements acquired from the system or (b) one or more vibration measurements and one or more performance parameter measurements acquired from the system;
  • condition signature is comprised of data from disparate sources, for instance performance and vibration data
  • a problem occurs in that the data may well not be synchronised in time. If this asynchronous data is combined to form the signature, a distorted picture of the system's health may well result.
  • training data used to develop a model of normal system behaviour should also be synchronised if distortions in the model are to be avoided.
  • condition indicators are synchronously acquired from the system to a synchronisation imprecision of at most 1 sec. More preferably the synchronisation imprecision is at most 0.1, 0.075, 0.0625 or 0.02 sec.
  • synchronisation imprecision we mean the maximum difference between the acquisition times of each pair of condition indicators forming a particular condition signature.
  • the measurements are acquired from the system at a synchronisation imprecision which is less than the duration of the successive time intervals, e.g. if the time intervals are of 0.2 sec duration, the synchronisation imprecision may be at most 0.075 sec.
  • the invention also provides a data processing system for monitoring the health of a system suitable for performing the method outlined above.
  • the data processing system comprises:
  • processor means for constructing a system condition signature from said plurality of measured condition indicators
  • comparator means for comparing the system condition signature with a predefined normal signature, corresponding to the signature for a healthy system
  • the data processing system may further comprise a display means for displaying (a) one or more of the condition indicators, (b) the result of the comparison of the system condition signature with the-normal signature and/or (c) an alert signal when the comparator indicates that the predetermined threshold has been transgressed (i.e. an event has been registered).
  • the invention provides a data processing system for monitoring the health of a system, comprising:
  • condition indicators including (a) a plurality of vibration measurements or (b) one or more vibration measurements and one or more performance parameter measurements;
  • processor means for constructing a condition signature from said condition indicators and for predicting a normal signature corresponding to the condition signature for a healthy system, the normal signature being predicted by a model which defines one or more inter-dependencies between said condition indicators;
  • comparator means for comparing the condition signature with the normal signature
  • registration means for registering an event if the comparator indicates that the condition signature differs from the normal signature by more than a predetermined threshold.
  • the invention provides a data processing system for monitoring the health of a system, comprising:
  • condition indicators including (a) a plurality of vibration measurements or (b) one or more vibration measurements and one or more performance parameter measurements;
  • processor means for constructing a condition signature from said condition indicators and for predicting a normal signature corresponding to the condition signature for a healthy system
  • comparator means for comparing the condition signature with the normal signature
  • registration means for registering an event if the comparator indicates that the condition signature differs from the normal signature by more than a predetermined threshold.
  • a further aspect of the invention addresses the problem of the synchronous acquisition of the condition indicators.
  • the invention proposes to associate time stamps (based on a common clock) with the acquired date and to synchronise the data on the basis of these time stamps.
  • the invention provides a method of synchronising two or more data streams, each data stream comprising a series of sequentially acquired data elements (and relating e.g. to a respective condition indicator of the previous aspect), the method comprising:
  • the common clock may be operate within an absolute or relative framework.
  • an absolute framework one clock provides the time stamp for each data element of each data stream.
  • each data stream has its own clock, and one of the clocks is selected as the reference clock against which the acquisition times of the other data streams are measured. It may be convenient to use a mixture of absolute and relative frameworks. For example, if the data streams relates to performance parameter and vibration measurements, the performance parameter measurements may be time stamped from one clock and the vibration measurements from another clock.
  • the process can be repeated until the data elements in the first stream have been exhausted. In any subsequent processing of the data that is reliant on using synchronised data streams, only those data elements marked as being synchronised with one another are used.
  • the first stream, with which the other streams are synchronised is chosen to be the stream having the lowest acquisition rate.
  • the invention further provides a data processing system for synchronising two or more data streams, each data stream comprising a series of sequentially acquired data elements, comprising:
  • FIG. 1 schematically illustrates an exemplary data structure that can be adopted for operation of the second aspect of the invention
  • FIG. 2 shows a neural network architecture for a learnt model for operation of the first aspect of the invention
  • FIG. 3 shows a graph of the prediction error for the learnt model on a set of test data corresponding to a period of normal operating conditions for an engine
  • FIG. 4 shows a graph of the prediction error for the learnt model for a further engine operating period in which the engine experienced a bird strike
  • FIG. 5 shows the learning curve for a simple example of a system model for operation of the first aspect of the invention
  • FIG. 6 shows a comparison of observations and modelled estimates for a shaft speed measurement, illustrating evolution of the model of FIG. 5 .
  • FIG. 7 shows the measured low pressure shaft speed (N1V) for the period of the test data from a more elaborate example of the system model
  • FIG. 8 shows the value for the NIS over the same period as FIG. 7 .
  • FIG. 9 shows the values for the 13 condition indicators and the NIS over the same period from a further example of the system model
  • FIG. 10 shows a schematic example of an on-the-engine health monitoring system.
  • the embodiment described below is an example of a data processing system employing both aspects of the invention discussed above. More specifically, it is a system for synchronous acquisition, analysis and display of performance parameters and vibration data from a power plant (e.g. a gas turbine), for monitoring the health of the plant.
  • a power plant e.g. a gas turbine
  • the performance and vibration data streams are synchronized in real time and, in accordance with a preferred aspect of the first aspect of the invention, these data are combined or fused to construct a signature for the system that can be compared to a signature derived from a model representing a healthy power plant, in order to provide anomaly/event detection and hence fault diagnosis.
  • the system acquires performance parameters from the gas turbine digitally via an ethernet link at a rate between 20 and 40 Hz. Typical performance parameters are measurements of pressure, temperature, thrust, altitude or Mach number. Vibration data is acquired from analogue vibration transducers which are sampled at user-selectable sampling rates (from 625 Hz to 80 kHz) via an analogue-to-digital converter. The amplitude spectrum of the vibration data is generated using the Fast Fourier Transform every 0.2 sec.
  • the performance and vibration data streams are asynchronous and stored in separate files together with the corresponding timestamps.
  • synchronisation is performed between the performance and spectrum data on a line by line basis.
  • Markers 10 , 12 (see FIG. 1 ) are kept which record the last synchronised line in the vibration and performance data ring buffers 14 , 16 .
  • the timestamp tar the next vibration spectrum line is examined.
  • the synchronisation algorithm starts from the last previously synchronised location in the performance data and searches forwards or backwards based on the timestamps of the performance data (accurate to 0.05 sec) until the closest matching timestamp in the performance data ring buffer 16 is identified. This location in the performance data is recorded as being synchronised with the line in the vibration ring buffer 14 .
  • the algorithm then proceeds to the next line in the vibration ring buffer 14 (0.2 sec later) and so on until there is no more data available to synchronise.
  • the synchronisation precision is 0.0625 sec.
  • the algorithm maintains a synchronisation table 18 that gives the index of the performance data entry that matches each vibration data line.
  • the algorithm uses variables to mark the latest synchronised data in each buffer.
  • the operation of the algorithm can be summarised by the following ‘pseudo code’:
  • vibration signatures to indicate engine state
  • gas-path analysis which is employed for determination of state from performance parameters.
  • performance-related parameters such as pressure and temperature can be fused with vibration data (such as tracked order vectors—the narrow range centered on the main vibration frequencies for each shaft of the turbine).
  • vibration data such as tracked order vectors—the narrow range centered on the main vibration frequencies for each shaft of the turbine.
  • the first method relies on a prior learnt model of normality.
  • normal vibration tracked order shapes are learnt using a simple clustering model for the normal data.
  • the novelty of e.g. the vibration signature for an engine under test is assessed by comparing the closeness of its tracked order signature with the prototypical patterns in the clustering model of normality. This can be done, for example, by computing the shortest normalised Euclidean distance between the vector encoding the tracked order shaped to any of the (prototypical patterns) cluster centers in the model of normality (see Nairac et al, “A System for the Analysis of Jet Engine Vibration Data”, Integrated Computer - Aided Engineering , 6(1):53-65, 1999).
  • the vibration signature as represented by that tracked order is deemed to be outside the bounds of normality.
  • the model of normality for the vibration spectra includes the following: sidebands, multiple harmonics, fractional harmonics and broadband power.
  • the model is illustrated by an example in which a neural network having the architecture shown in FIG. 2 was developed as the learnt model.
  • the neural network had an input layer 30 with four nodes for a condition signature consisting of four condition indicators measured relating to one shaft of a multi-shaft test engine.
  • the condition indicators were the vibration amplitude, the phase and the shaft speed all at a specified time, and the shaft speed a time increment after the specified time.
  • the output layer 32 of the network had two nodes for predicting respectively the change in vibration amplitude and change in phase after the time increment.
  • the network had one hidden layer 34 , each node of which contained a Gaussian radial basis function.
  • the training phase for network used training data obtained from the test engine over a range of normal operating conditions.
  • the centers and the spreads of the Gaussians were fixed using the cluster analysis described above and the weights of the connections between the nodes were then iteratively adjusted until the model converged.
  • FIG. 3 shows a graph of the prediction error (i.e. the sum of the prediction errors of the change in vibration amplitude and change in phase) for the model on a set of test data which also corresponded to a period of normal operating conditions for the engine. This graph provides a baseline of prediction error variation against which novel events can be judged.
  • FIG. 4 shows a graph of the prediction error for a further engine operating period.
  • the engine experienced a bird strike.
  • the largest peak in the graph corresponds to the moment of bird impact.
  • the model was able to recognise this event.
  • the changed prediction error signal (compared to the baseline of FIG. 3 ) after the event showed that the model was also able to detect post-impact abnormal engine behaviour. This provides confidence that the model can not only detect major events such as bird strikes, but also more subtle deviations from normality.
  • the second method employs a process model which has a state vector associated with it (see below).
  • the observation vector i.e. the condition signature
  • the observation vector has elements corresponding to measured values of performance parameters and vibration information so that two types of data are fused within the model.
  • the fusion of the data is performed in real-time with a new output being generated by the system several times a second.
  • a generic model of the engine is learnt.
  • the learning is data-driven using an algorithm such as Expectation-Maximisation in order to maximise the likelihood of the learnt model given the training data.
  • an algorithm such as Expectation-Maximisation in order to maximise the likelihood of the learnt model given the training data.
  • learnt model can then be applied on-line in order to tune the model to an individual engine immediately after its pass-off test and after each maintenance procedure. Engine deterioration can also be learnt on-line.
  • the learnt model can be tuned to different flight conditions, such as cruising or landing, in order to detect novelty with even more sensitivity and specificity.
  • the data-driven learnt model may be integrated with existing performance models which rely on the laws of thermodynamics and computational fluid dynamics (knowledge-based models). Such models can therefore be described as hybrid models because they are based on the integration of learnt and knowledge-based models.
  • the EM learning algorithm is applied to a Kalman filter model.
  • y(i) is a set of observations of hidden state x(i)
  • C is a covariance matrix
  • measurement noise v(i) is zero-mean and normally distributed with covariance matrix R.
  • y(i) and x(i) can be the same dimension.
  • Non-zero off-diagonal terms in C allow the model to account for inter-dependencies between the performance parameter and vibration measurements of the condition and normal signatures.
  • a and C are initialised to small random values (e.g. with elements of the matrices ⁇ 10 ⁇ 5 ), and R and Q are initialised e.g. to I.
  • the elements of C, R and v(i) are iteratively adjusted so that Cx(i)+v(i) converges to the respective condition signature (R and Q can be constrained throughout to be diagonal matrices).
  • Convergence can be determined by the log-likelihood of the set of observations given the model.
  • the model would then be a hybrid of a knowledge-based and a data-driven model. By fusing these two methods of data-analysis, the accuracy of prior expert knowledge can be combined with the robustness of data-driven approaches.
  • the Kalman filter is again used to derive the most likely values for the elements of x(i) for each condition signature y(i).
  • the elements of C and v(i) are now fixed, so Cx(i)+v(i) provides the normal signature for comparison with the condition signature.
  • comparison of the normal signature with the condition signature can be on the basis of the normalised innovations squared (NIS).
  • NIS normalised innovations squared
  • the innovations should be zero-mean and white.
  • NIS ( k ) v T ( k ) S ( k ) ⁇ 1 v ( k ) (4)
  • the model is first illustrated by a simple example (which does not use vibration measurements) where observations are made of the speeds of the three shafts of a test engine during cruise.
  • the observations are used during the learning process, to generate a dynamical system model in which A, C, Q and R are learned from the data.
  • a and C were initialised to small random values and R and Q were initialised to I.
  • FIG. 5 illustrates the learning (log likelihood) plot for the system.
  • FIG. 6 shows the evolution of estimates of shaft 1 speeds during the learning process using the EM algorithm.
  • the learning stage lasts for the first 25 iterations. From iteration 25 onwards, the system's dynamical properties are determined by the learned matrices (which are then kept fixed).
  • the systems can be used to detect events or abnormalities, that is to say divergences from the learnt model of normality.
  • the events of particular interest are those that are unexpected, possibly indicating a problem with the engine for example.
  • transients during operation of the engine will also be flagged up as events, although they are expected. For example, where a bleed valve is opened or closed, the operating condition of the engine will exhibit significant differences from a learnt model of steady state normality which does not include this event.
  • measures can be employed to avoid these transient events. For instance, since the opening of a bleed valve is an event that occurs at a defined point in time, the data collected from the engine at that time and slightly either side of it (e.g. for 2 seconds before and after) can be eliminated from the data analysed by the health monitoring system.
  • the training data was 152-00 data for a period before the event, and the test data was 152-00 data for the period including the event.
  • a 14 dimensional model i.e. y(i) and x(i) each had 14 elements
  • the condition indicator inputs were:
  • the demanded fuel flow (WFDEM)
  • FIG. 7 shows the measured low pressure shaft speed (N1V) for part of the period of the test data
  • FIG. 8 shows the value for the NIS calculated by the trained model over the same period.
  • the first two sharp troughs in the N1V trace were caused by planned consecutive cyclic decelerations. Associated with each of these troughs are two NIS peaks. These peaks indicated that the engine was not behaving normally during the cyclic testing. In fact subsequent examination revealed that a lock plate had released earlier during the test and as a result abnormal blade rubbing Was occurring during each of the deceleration cycles.
  • NIS peaks demonstrate that the monitoring system was able to detect the effect of the lock plate release in real time and before substantial blade damage was sustained. If such a release had occurred in an in-service aero engine, it would therefore have been possible to generate an immediate warning so that timely action (such as engine inspection or maintenance) could have been performed. In contrast, sudden variations in N1V can occur normally, so N1V alone is not a reliable indicator of abnormal behaviour.
  • a further example also uses both performance parameter and vibration data. Again the model was applied to synchronously data acquired from a test bed-mounted, multi-shaft, aero gas turbine engine. However, in this case an oil seal leak developed in the engine.
  • the fault occurred in the engine around data point 50410 .
  • the training data was from a period before the fault, and the test data was for a period including the fault.
  • a 13 dimensional model was used in which the condition indicator inputs were tol, toi, toh, N1V, N2V, N3V, P0V, P20V, P30V, PEXV, T20V, TGTTRM, and WFDEM.
  • FIG. 9 shows the values for the 13 condition indicators and the NIS (in the bottom graph) over the period including the event.
  • the sharp NIS peak at data point 50410 again demonstrates that the monitoring system was able to detect the moment of the event.
  • some of the other condition indicators also had peaks at this time, by themselves they cannot be reliably associated with abnormal (novel) behaviour.
  • An on-the-engine system shown schematically in FIG. 10 , could generate of the order of 1 Gb of vibration and performance data (consisting mainly of pressures, temperatures and shaft speeds) per flight.
  • the vibration data is usually analysed in the frequency domain.
  • the vibration and performance data, as they are being generated by data acquisition means 20 are temporarily stored in ring buffer 22 .
  • the data is synchronised and subjected to novelty detection in processor and comparator means 24 which receives a synchronisation signal from data acquisition means 20 and the data from ring buffer 22 .
  • Those sections of the data corresponding to novel events are then tagged and recorded with no loss of information (i.e. highbandwidth data is recorded) in registration means 26 which has semi-permanent on-line and/or hard disk storage.
  • the stored data may be downloaded and subjected to more intensive ground-based analysis.
  • the system may also include a display which is driven to allow information to be displayed either during acquisition or for review once an acquisition cycle has been completed. It preferably includes the following features:

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Evolutionary Computation (AREA)
  • Acoustics & Sound (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Paper (AREA)
  • Control Of Steam Boilers And Waste-Gas Boilers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Investigating Or Analysing Materials By The Use Of Chemical Reactions (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Debugging And Monitoring (AREA)
US09/898,008 2000-07-05 2001-07-05 Health monitoring Expired - Lifetime US6928370B2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GBGB0016561.3A GB0016561D0 (en) 2000-07-05 2000-07-05 Health monitoring
GB0016561.3 2000-07-05

Publications (2)

Publication Number Publication Date
US20020040278A1 US20020040278A1 (en) 2002-04-04
US6928370B2 true US6928370B2 (en) 2005-08-09

Family

ID=9895110

Family Applications (1)

Application Number Title Priority Date Filing Date
US09/898,008 Expired - Lifetime US6928370B2 (en) 2000-07-05 2001-07-05 Health monitoring

Country Status (10)

Country Link
US (1) US6928370B2 (de)
EP (1) EP1297313B1 (de)
JP (1) JP4859328B2 (de)
AT (1) ATE441836T1 (de)
AU (1) AU2001267749A1 (de)
DE (1) DE60139778D1 (de)
DK (1) DK1297313T3 (de)
ES (1) ES2332874T3 (de)
GB (1) GB0016561D0 (de)
WO (1) WO2002003041A1 (de)

Cited By (103)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030176954A1 (en) * 2001-10-12 2003-09-18 Jaw Link C. Tracking and control of gas turbine engine component damage/life
US20050027205A1 (en) * 2001-12-14 2005-02-03 Lionel Tarassenko Combining measurements from breathing rate sensors
US20050049834A1 (en) * 2001-02-27 2005-03-03 Bottomfield Roger L. Non-invasive system and method for diagnosing potential malfunctions of semiconductor equipment components
US20050171705A1 (en) * 2003-11-18 2005-08-04 Peter Renner Condition monitoring in technical processes
US20070067114A1 (en) * 2005-09-16 2007-03-22 D Amato Fernando J System and method for monitoring degradation
US20070191697A1 (en) * 2006-02-10 2007-08-16 Lynn Lawrence A System and method for SPO2 instability detection and quantification
US20070282478A1 (en) * 2006-06-05 2007-12-06 Ammar Al-Ali Parameter upgrade system
US20080020037A1 (en) * 2006-07-11 2008-01-24 Robertson Timothy L Acoustic Pharma-Informatics System
US20080027568A1 (en) * 2006-07-27 2008-01-31 Scott Allan Pearson Method and Apparatus for Equipment Health Monitoring
US20080140352A1 (en) * 2006-12-07 2008-06-12 General Electric Company System and method for equipment life estimation
US20080140360A1 (en) * 2006-12-07 2008-06-12 General Electric Company System and method for damage propagation estimation
US20080316020A1 (en) * 2007-05-24 2008-12-25 Robertson Timothy L Rfid antenna for in-body device
US20090299695A1 (en) * 2008-05-29 2009-12-03 General Electric Company System and method for advanced condition monitoring of an asset system
US7647185B2 (en) 2000-06-16 2010-01-12 Oxford Biosignals Limited Combining measurements from different sensors
US20100082295A1 (en) * 2008-10-01 2010-04-01 Klaus Gram-Hansen Method and System of Wind Turbine Condition Monitoring
US20100298668A1 (en) * 2008-08-13 2010-11-25 Hooman Hafezi Ingestible Circuitry
US20110015501A1 (en) * 1997-01-27 2011-01-20 Lynn Lawrence A Microprocessor system for the analysis of physiologic and financial datasets
US7978064B2 (en) 2005-04-28 2011-07-12 Proteus Biomedical, Inc. Communication system with partial power source
US7990382B2 (en) 2006-01-03 2011-08-02 Masimo Corporation Virtual display
US8036748B2 (en) 2008-11-13 2011-10-11 Proteus Biomedical, Inc. Ingestible therapy activator system and method
US8054140B2 (en) 2006-10-17 2011-11-08 Proteus Biomedical, Inc. Low voltage oscillator for medical devices
US20110307220A1 (en) * 2008-12-15 2011-12-15 Snecma Identifying failures in an aeroengine
US8114021B2 (en) 2008-12-15 2012-02-14 Proteus Biomedical, Inc. Body-associated receiver and method
US8187201B2 (en) 1997-01-27 2012-05-29 Lynn Lawrence A System and method for applying continuous positive airway pressure
US8258962B2 (en) 2008-03-05 2012-09-04 Proteus Biomedical, Inc. Multi-mode communication ingestible event markers and systems, and methods of using the same
US8274360B2 (en) 2007-10-12 2012-09-25 Masimo Corporation Systems and methods for storing, analyzing, and retrieving medical data
US8310336B2 (en) 2008-10-10 2012-11-13 Masimo Corporation Systems and methods for storing, analyzing, retrieving and displaying streaming medical data
US20130103326A1 (en) * 2011-10-20 2013-04-25 William A. Von Drasek Method for early warning chatter detection and asset protection management
US8540664B2 (en) 2009-03-25 2013-09-24 Proteus Digital Health, Inc. Probablistic pharmacokinetic and pharmacodynamic modeling
US8545402B2 (en) 2009-04-28 2013-10-01 Proteus Digital Health, Inc. Highly reliable ingestible event markers and methods for using the same
US8547248B2 (en) 2005-09-01 2013-10-01 Proteus Digital Health, Inc. Implantable zero-wire communications system
US8558563B2 (en) 2009-08-21 2013-10-15 Proteus Digital Health, Inc. Apparatus and method for measuring biochemical parameters
US8583227B2 (en) 2008-12-11 2013-11-12 Proteus Digital Health, Inc. Evaluation of gastrointestinal function using portable electroviscerography systems and methods of using the same
US8597186B2 (en) 2009-01-06 2013-12-03 Proteus Digital Health, Inc. Pharmaceutical dosages delivery system
US20130338982A1 (en) * 2012-06-13 2013-12-19 Robert B. Schwab Engine Vibration And Engine Trim Balance Test System, Apparatus And Method
US8718193B2 (en) 2006-11-20 2014-05-06 Proteus Digital Health, Inc. Active signal processing personal health signal receivers
US8728001B2 (en) 2006-02-10 2014-05-20 Lawrence A. Lynn Nasal capnographic pressure monitoring system
US8730031B2 (en) 2005-04-28 2014-05-20 Proteus Digital Health, Inc. Communication system using an implantable device
US8784308B2 (en) 2009-12-02 2014-07-22 Proteus Digital Health, Inc. Integrated ingestible event marker system with pharmaceutical product
US8802183B2 (en) 2005-04-28 2014-08-12 Proteus Digital Health, Inc. Communication system with enhanced partial power source and method of manufacturing same
US8836513B2 (en) 2006-04-28 2014-09-16 Proteus Digital Health, Inc. Communication system incorporated in an ingestible product
US8858432B2 (en) 2007-02-01 2014-10-14 Proteus Digital Health, Inc. Ingestible event marker systems
US8868453B2 (en) 2009-11-04 2014-10-21 Proteus Digital Health, Inc. System for supply chain management
US8912908B2 (en) 2005-04-28 2014-12-16 Proteus Digital Health, Inc. Communication system with remote activation
US8920317B2 (en) 2003-07-25 2014-12-30 Masimo Corporation Multipurpose sensor port
US8932221B2 (en) 2007-03-09 2015-01-13 Proteus Digital Health, Inc. In-body device having a multi-directional transmitter
US8945005B2 (en) 2006-10-25 2015-02-03 Proteus Digital Health, Inc. Controlled activation ingestible identifier
US8956287B2 (en) 2006-05-02 2015-02-17 Proteus Digital Health, Inc. Patient customized therapeutic regimens
US8956288B2 (en) 2007-02-14 2015-02-17 Proteus Digital Health, Inc. In-body power source having high surface area electrode
US8961412B2 (en) 2007-09-25 2015-02-24 Proteus Digital Health, Inc. In-body device with virtual dipole signal amplification
US9014918B2 (en) 2012-10-12 2015-04-21 Cummins Inc. Health monitoring systems and techniques for vehicle systems
US9014779B2 (en) 2010-02-01 2015-04-21 Proteus Digital Health, Inc. Data gathering system
US9031793B2 (en) 2001-05-17 2015-05-12 Lawrence A. Lynn Centralized hospital monitoring system for automatically detecting upper airway instability and for preventing and aborting adverse drug reactions
US9032785B1 (en) 2011-07-01 2015-05-19 The United States Of America As Represented By The Administrator National Aeronautics And Space Administration Method for making measurements of the post-combustion residence time in a gas turbine engine
US9042952B2 (en) 1997-01-27 2015-05-26 Lawrence A. Lynn System and method for automatic detection of a plurality of SPO2 time series pattern types
US9053222B2 (en) 2002-05-17 2015-06-09 Lawrence A. Lynn Patient safety processor
US9107806B2 (en) 2010-11-22 2015-08-18 Proteus Digital Health, Inc. Ingestible device with pharmaceutical product
US9149423B2 (en) 2009-05-12 2015-10-06 Proteus Digital Health, Inc. Ingestible event markers comprising an ingestible component
US9198608B2 (en) 2005-04-28 2015-12-01 Proteus Digital Health, Inc. Communication system incorporated in a container
US9218454B2 (en) 2009-03-04 2015-12-22 Masimo Corporation Medical monitoring system
US9235683B2 (en) 2011-11-09 2016-01-12 Proteus Digital Health, Inc. Apparatus, system, and method for managing adherence to a regimen
US9270503B2 (en) 2013-09-20 2016-02-23 Proteus Digital Health, Inc. Methods, devices and systems for receiving and decoding a signal in the presence of noise using slices and warping
US9270025B2 (en) 2007-03-09 2016-02-23 Proteus Digital Health, Inc. In-body device having deployable antenna
US9268909B2 (en) 2012-10-18 2016-02-23 Proteus Digital Health, Inc. Apparatus, system, and method to adaptively optimize power dissipation and broadcast power in a power source for a communication device
US9271897B2 (en) 2012-07-23 2016-03-01 Proteus Digital Health, Inc. Techniques for manufacturing ingestible event markers comprising an ingestible component
US9323894B2 (en) 2011-08-19 2016-04-26 Masimo Corporation Health care sanitation monitoring system
US9439599B2 (en) 2011-03-11 2016-09-13 Proteus Digital Health, Inc. Wearable personal body associated device with various physical configurations
US9439566B2 (en) 2008-12-15 2016-09-13 Proteus Digital Health, Inc. Re-wearable wireless device
US9468378B2 (en) 1997-01-27 2016-10-18 Lawrence A. Lynn Airway instability detection system and method
US9521971B2 (en) 1997-07-14 2016-12-20 Lawrence A. Lynn System and method for automatic detection of a plurality of SPO2 time series pattern types
US9577864B2 (en) 2013-09-24 2017-02-21 Proteus Digital Health, Inc. Method and apparatus for use with received electromagnetic signal at a frequency not known exactly in advance
US9597487B2 (en) 2010-04-07 2017-03-21 Proteus Digital Health, Inc. Miniature ingestible device
US9603550B2 (en) 2008-07-08 2017-03-28 Proteus Digital Health, Inc. State characterization based on multi-variate data fusion techniques
US9659423B2 (en) 2008-12-15 2017-05-23 Proteus Digital Health, Inc. Personal authentication apparatus system and method
US9733141B1 (en) 2012-06-27 2017-08-15 The United States Of America As Represented By The Administrator Of National Aeronautics And Space Administration Method for making measurements of the post-combustion residence time in a gas turbine engine
US9756874B2 (en) 2011-07-11 2017-09-12 Proteus Digital Health, Inc. Masticable ingestible product and communication system therefor
US9796576B2 (en) 2013-08-30 2017-10-24 Proteus Digital Health, Inc. Container with electronically controlled interlock
US9795739B2 (en) 2009-05-20 2017-10-24 Masimo Corporation Hemoglobin display and patient treatment
US9883819B2 (en) 2009-01-06 2018-02-06 Proteus Digital Health, Inc. Ingestion-related biofeedback and personalized medical therapy method and system
US10007758B2 (en) 2009-03-04 2018-06-26 Masimo Corporation Medical monitoring system
US10032002B2 (en) 2009-03-04 2018-07-24 Masimo Corporation Medical monitoring system
US10084880B2 (en) 2013-11-04 2018-09-25 Proteus Digital Health, Inc. Social media networking based on physiologic information
US20180306677A1 (en) * 2015-10-13 2018-10-25 Nec Corporation Structure abnormality detection device, structure abnormality detection method, storage medium, and structure abnormality detection system
US10175376B2 (en) 2013-03-15 2019-01-08 Proteus Digital Health, Inc. Metal detector apparatus, system, and method
US10187121B2 (en) 2016-07-22 2019-01-22 Proteus Digital Health, Inc. Electromagnetic sensing and detection of ingestible event markers
US10223905B2 (en) 2011-07-21 2019-03-05 Proteus Digital Health, Inc. Mobile device and system for detection and communication of information received from an ingestible device
US10275570B2 (en) 2012-12-31 2019-04-30 Cerner Innovation, Inc. Closed loop alert management
US10379713B2 (en) 2012-10-05 2019-08-13 Cerner Innovation, Inc. Multi-action button for mobile devices
US10388413B2 (en) 2015-12-30 2019-08-20 Cerner Innovation, Inc. Intelligent alert suppression
US10398161B2 (en) 2014-01-21 2019-09-03 Proteus Digital Heal Th, Inc. Masticable ingestible product and communication system therefor
US10529044B2 (en) 2010-05-19 2020-01-07 Proteus Digital Health, Inc. Tracking and delivery confirmation of pharmaceutical products
US10580279B2 (en) 2012-12-31 2020-03-03 Cerner Innovation, Inc. Alert management utilizing mobile devices
US10607728B2 (en) 2015-10-06 2020-03-31 Cerner Innovation, Inc. Alert optimizer
US10941725B2 (en) 2017-06-27 2021-03-09 Rolls-Royce Corporation Vibration feedback controller
US10957445B2 (en) 2017-10-05 2021-03-23 Hill-Rom Services, Inc. Caregiver and staff information system
US11041271B2 (en) 2017-10-24 2021-06-22 Ecolab Usa Inc. Deposit detection in a paper making system via vibration analysis
US11051543B2 (en) 2015-07-21 2021-07-06 Otsuka Pharmaceutical Co. Ltd. Alginate on adhesive bilayer laminate film
US11149123B2 (en) 2013-01-29 2021-10-19 Otsuka Pharmaceutical Co., Ltd. Highly-swellable polymeric films and compositions comprising the same
US11158149B2 (en) 2013-03-15 2021-10-26 Otsuka Pharmaceutical Co., Ltd. Personal authentication apparatus system and method
US11317837B2 (en) 2006-10-12 2022-05-03 Masimo Corporation System and method for monitoring the life of a physiological sensor
US11455848B2 (en) 2019-09-27 2022-09-27 Ge Aviation Systems Limited Preserving vehicular raw vibration data for post-event analysis
US11529071B2 (en) 2016-10-26 2022-12-20 Otsuka Pharmaceutical Co., Ltd. Methods for manufacturing capsules with ingestible event markers
US11744481B2 (en) 2013-03-15 2023-09-05 Otsuka Pharmaceutical Co., Ltd. System, apparatus and methods for data collection and assessing outcomes

Families Citing this family (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1374167B1 (de) * 2001-03-08 2010-05-12 California Institute Of Technology Raumzeitliche echtzeit-kohärenzschätzung zur autonom-modusidentifikation und invarianzverfolgung
FR2824395B1 (fr) * 2001-05-04 2004-09-10 Eurocopter France Procede et dispositif pour detecter des defauts d'au moins un rotor d'un aeronef a voilure tournante, en particulier d'un helicoptere, et pour regler ce rotor
US6999884B2 (en) 2003-01-10 2006-02-14 Oxford Biosignals Limited Bearing anomaly detection and location
US6961677B1 (en) * 2003-08-25 2005-11-01 Itt Manufacturing Enterprises, Inc. Method and apparatus for categorizing unexplained residuals
GB0400840D0 (en) * 2004-01-15 2004-02-18 Rolls Royce Plc Method of processing oscillatory data
EP1560338A1 (de) * 2004-01-27 2005-08-03 Siemens Aktiengesellschaft Verfahren zur Speicherung von Prozesssignalen einer technischen Anlage
GB0417421D0 (en) * 2004-08-05 2004-09-08 Rolls Royce Plc Method of processing oscillatory data
US7280941B2 (en) 2004-12-29 2007-10-09 General Electric Company Method and apparatus for in-situ detection and isolation of aircraft engine faults
GB0518659D0 (en) 2005-09-13 2005-10-19 Rolls Royce Plc Health monitoring
US8795170B2 (en) 2005-11-29 2014-08-05 Venture Gain LLC Residual based monitoring of human health
US7577548B1 (en) * 2006-03-04 2009-08-18 Hrl Laboratories Integrated framework for diagnosis and prognosis of components
EP2053475A1 (de) * 2007-10-26 2009-04-29 Siemens Aktiengesellschaft Verfahren zur Analyse des Betriebs einer Gasturbine
GB0818544D0 (en) 2008-10-09 2008-11-19 Oxford Biosignals Ltd Improvements in or relating to multi-parameter monitoring
US8321118B2 (en) * 2008-12-23 2012-11-27 Honeywell International Inc. Operations support systems and methods with power assurance
US8306778B2 (en) * 2008-12-23 2012-11-06 Embraer S.A. Prognostics and health monitoring for electro-mechanical systems and components
US20110106747A1 (en) * 2009-10-30 2011-05-05 General Electric Company Turbine life assessment and inspection system and methods
US8862433B2 (en) 2010-05-18 2014-10-14 United Technologies Corporation Partitioning of turbomachine faults
US9466032B2 (en) 2011-06-03 2016-10-11 Siemens Aktiengesellschaft Method for the computer-supported generation of a data-driven model of a technical system, in particular of a gas turbine or wind turbine
EP2626696A1 (de) * 2012-02-10 2013-08-14 Acosense AB Akustisches Messsystem mit Ringpuffer
US10330018B2 (en) * 2014-03-24 2019-06-25 Rolls-Royce Corporation Integrating design and field management of gas turbine engine components with a probabilistic model
US9846426B2 (en) * 2014-07-28 2017-12-19 Computational Systems, Inc. Parallel digital signal processing of machine vibration data
EP3327419B1 (de) * 2016-11-29 2020-09-09 STS Intellimon Limited Motordiagnosevorrichtung und -verfahren
US11226615B2 (en) 2017-05-02 2022-01-18 Lateral Solutions, Inc. Control system for machine with a plurality of components and methods of operation
JP6947077B2 (ja) * 2018-02-26 2021-10-13 株式会社Ihi ガスタービンの整備時期予測方法及びその装置
CN108535358A (zh) * 2018-04-10 2018-09-14 沈阳化工大学 一种变壁厚回转工件缺陷检测装置及其方法
WO2019215807A1 (ja) * 2018-05-08 2019-11-14 日本電気株式会社 監視装置、学習装置、監視方法、学習方法及び記憶媒体
DE102018115354A1 (de) * 2018-06-26 2020-01-02 Rolls-Royce Deutschland Ltd & Co Kg Vorrichtung und Verfahren zur Bestimmung mindestens eines Rotationsparameters einer rotierenden Vorrichtung
CN109142547B (zh) * 2018-08-08 2021-02-23 广东省智能制造研究所 一种基于卷积神经网络的声学在线无损检测方法
CN110697075B (zh) * 2019-09-29 2022-11-25 中国直升机设计研究所 一种直升机hums振动阈值生成方法
CN111257415B (zh) * 2020-01-17 2021-08-10 同济大学 基于移动列车振动信号的隧道损伤检测管理系统

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2135061A (en) 1982-07-06 1984-08-22 Ford Motor Co Frequency domain engine defect signal analysis
GB2256491A (en) 1991-06-06 1992-12-09 Bosch Gmbh Robert Misfire recognition in an engine.
US5206816A (en) * 1991-01-30 1993-04-27 Westinghouse Electric Corp. System and method for monitoring synchronous blade vibration
US5210704A (en) * 1990-10-02 1993-05-11 Technology International Incorporated System for prognosis and diagnostics of failure and wearout monitoring and for prediction of life expectancy of helicopter gearboxes and other rotating equipment
GB2277151A (en) 1993-04-05 1994-10-19 Univ Brunel Machine monitoring using neural network
US5402521A (en) 1990-02-28 1995-03-28 Chiyoda Corporation Method for recognition of abnormal conditions using neural networks
US5684718A (en) 1996-02-12 1997-11-04 Westinghouse Electric Corporation Method and apparatus for monitoring the operation of an electric generator
US5774376A (en) * 1995-08-07 1998-06-30 Manning; Raymund A. Structural health monitoring using active members and neural networks
US5784273A (en) * 1996-11-07 1998-07-21 Madhavan; Poovanpilli G. Method and system for predicting limit cycle oscillations and control method and system utilizing same
US5847658A (en) * 1995-08-15 1998-12-08 Omron Corporation Vibration monitor and monitoring method
EP0908805A1 (de) 1995-04-05 1999-04-14 Dayton T. Brown, Inc. Methode und Vorrichtung zur preemptiven Wartung eines Betriebsgerätes
US5995910A (en) * 1997-08-29 1999-11-30 Reliance Electric Industrial Company Method and system for synthesizing vibration data
EP1014054A2 (de) 1998-12-24 2000-06-28 SCHENCK VIBRO GmbH Verfahren zur modellbasierten schwingungsdiagnostischen Überwachung rotierenden Maschinen
GB2349952A (en) 1999-05-03 2000-11-15 Ford Global Tech Inc Real-time engine misfire detection method involving the calculation of a karlovitz number

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US568718A (en) * 1896-09-29 George
JPH04211859A (ja) * 1990-02-28 1992-08-03 Chiyoda Corp 異常認知方法
JPH063215A (ja) * 1992-06-19 1994-01-11 Kao Corp 回転機器の診断方法及び診断装置
JPH06109498A (ja) * 1992-09-29 1994-04-19 Toshiba Corp 非定常および異常状態の検出装置
JPH0990027A (ja) * 1995-09-20 1997-04-04 Mitsubishi Electric Corp 目標曲進判定装置
US6216066B1 (en) * 1998-07-01 2001-04-10 General Electric Company System and method for generating alerts through multi-variate data assessment

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2135061A (en) 1982-07-06 1984-08-22 Ford Motor Co Frequency domain engine defect signal analysis
US5402521A (en) 1990-02-28 1995-03-28 Chiyoda Corporation Method for recognition of abnormal conditions using neural networks
US5210704A (en) * 1990-10-02 1993-05-11 Technology International Incorporated System for prognosis and diagnostics of failure and wearout monitoring and for prediction of life expectancy of helicopter gearboxes and other rotating equipment
US5206816A (en) * 1991-01-30 1993-04-27 Westinghouse Electric Corp. System and method for monitoring synchronous blade vibration
GB2256491A (en) 1991-06-06 1992-12-09 Bosch Gmbh Robert Misfire recognition in an engine.
GB2277151A (en) 1993-04-05 1994-10-19 Univ Brunel Machine monitoring using neural network
EP0908805A1 (de) 1995-04-05 1999-04-14 Dayton T. Brown, Inc. Methode und Vorrichtung zur preemptiven Wartung eines Betriebsgerätes
US5774376A (en) * 1995-08-07 1998-06-30 Manning; Raymund A. Structural health monitoring using active members and neural networks
US5847658A (en) * 1995-08-15 1998-12-08 Omron Corporation Vibration monitor and monitoring method
US5684718A (en) 1996-02-12 1997-11-04 Westinghouse Electric Corporation Method and apparatus for monitoring the operation of an electric generator
US5784273A (en) * 1996-11-07 1998-07-21 Madhavan; Poovanpilli G. Method and system for predicting limit cycle oscillations and control method and system utilizing same
US5995910A (en) * 1997-08-29 1999-11-30 Reliance Electric Industrial Company Method and system for synthesizing vibration data
EP1014054A2 (de) 1998-12-24 2000-06-28 SCHENCK VIBRO GmbH Verfahren zur modellbasierten schwingungsdiagnostischen Überwachung rotierenden Maschinen
GB2349952A (en) 1999-05-03 2000-11-15 Ford Global Tech Inc Real-time engine misfire detection method involving the calculation of a karlovitz number

Non-Patent Citations (11)

* Cited by examiner, † Cited by third party
Title
"Application of a Neural Network in Gas Turbine Control Sensor Fault Detection", Simani et al., Proceeding of the 1998 IEEE International Conference on Control Applications, Trieste, Italy, Sep. 1-4, 1998. *
Caulkins et al., Applying Neural Networks to Determine Vibration Parameters in a Turbine, 1999 IEEE. *
DePold et al., The Application of Expert Systems and Neural Networks to Gas Turbine Prognostics and Diagnostics, Oct. 1999, Journal of Engineering for Gas Turbines and Power, vol. 121, pp. 607-612. *
Gelb et al., " Applied Optimal Estimation", MIT Press 1974, pp. 102-155.
Ghahramani et al., "Learning Nonlinear Dynamical Systems using an EM Algorithm", in Kearns et al. (ed), Advances in Neural Information Processing Systems, vol. 11, MIT Press, 1999.
Ghahramani et al., "Parameter Estimation for Linear Dynamical Systems", Technical Report CRG-TR-96-2, University of Toronto, Feb. 22, 1996, pp. 1-6.
Greitzer et al., Gas Turbine Engine Health Monitoring and Prognostics, Aug. 30-Sep. 2, 1999, International Society of Logistics (SOLE) Symposium. *
Nairac et al., "A System for the Analysis of Jet Engine Vibration Data", Integrated Computer-Aided Engineering, vol. 6, No. 1, pp. 53-65, 1999.
Patel et al., Gas Turbine Engine Condition Monitoring Using Statistical and Neural Network Methods, 1996, The Institution of Electrical Engineers, IEE. *
Roweis et al., "A Unifying Review of Linear Gaussian Models", Neural Computation, vol. 11, 1999, pp. 305-345.
X, Li et al. "Fault prognosis for large rotating machinery using neural network" Application of artificial intelligence in engineering IX. Proceedings of the ninth international conference, proceedings of ninth international conference on applications of artificial intelligence in engineering. Aieng 94, Malvern, PA, USA 19-21 J, pp. 99-105.

Cited By (207)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8152732B2 (en) 1992-08-19 2012-04-10 Lynn Lawrence A Microprocessor system for the analysis of physiologic and financial datasets
US9042952B2 (en) 1997-01-27 2015-05-26 Lawrence A. Lynn System and method for automatic detection of a plurality of SPO2 time series pattern types
US20110015501A1 (en) * 1997-01-27 2011-01-20 Lynn Lawrence A Microprocessor system for the analysis of physiologic and financial datasets
US8187201B2 (en) 1997-01-27 2012-05-29 Lynn Lawrence A System and method for applying continuous positive airway pressure
US8241213B2 (en) 1997-01-27 2012-08-14 Lynn Lawrence A Microprocessor system for the analysis of physiologic datasets
US9468378B2 (en) 1997-01-27 2016-10-18 Lawrence A. Lynn Airway instability detection system and method
US9521971B2 (en) 1997-07-14 2016-12-20 Lawrence A. Lynn System and method for automatic detection of a plurality of SPO2 time series pattern types
US7647185B2 (en) 2000-06-16 2010-01-12 Oxford Biosignals Limited Combining measurements from different sensors
US8932227B2 (en) 2000-07-28 2015-01-13 Lawrence A. Lynn System and method for CO2 and oximetry integration
US10058269B2 (en) 2000-07-28 2018-08-28 Lawrence A. Lynn Monitoring system for identifying an end-exhalation carbon dioxide value of enhanced clinical utility
US20050049834A1 (en) * 2001-02-27 2005-03-03 Bottomfield Roger L. Non-invasive system and method for diagnosing potential malfunctions of semiconductor equipment components
US9031793B2 (en) 2001-05-17 2015-05-12 Lawrence A. Lynn Centralized hospital monitoring system for automatically detecting upper airway instability and for preventing and aborting adverse drug reactions
US8862196B2 (en) 2001-05-17 2014-10-14 Lawrence A. Lynn System and method for automatic detection of a plurality of SP02 time series pattern types
US11439321B2 (en) 2001-05-17 2022-09-13 Lawrence A. Lynn Monitoring system for identifying an end-exhalation carbon dioxide value of enhanced clinical utility
US20030176954A1 (en) * 2001-10-12 2003-09-18 Jaw Link C. Tracking and control of gas turbine engine component damage/life
US7318808B2 (en) 2001-12-14 2008-01-15 Isis Innovation Limited Combining measurements from breathing rate sensors
US20050027205A1 (en) * 2001-12-14 2005-02-03 Lionel Tarassenko Combining measurements from breathing rate sensors
US9053222B2 (en) 2002-05-17 2015-06-09 Lawrence A. Lynn Patient safety processor
US8920317B2 (en) 2003-07-25 2014-12-30 Masimo Corporation Multipurpose sensor port
US11020029B2 (en) 2003-07-25 2021-06-01 Masimo Corporation Multipurpose sensor port
US10058275B2 (en) 2003-07-25 2018-08-28 Masimo Corporation Multipurpose sensor port
US7113871B2 (en) * 2003-11-18 2006-09-26 Peter Renner Condition monitoring in technical processes
US20050171705A1 (en) * 2003-11-18 2005-08-04 Peter Renner Condition monitoring in technical processes
US9161707B2 (en) 2005-04-28 2015-10-20 Proteus Digital Health, Inc. Communication system incorporated in an ingestible product
US9962107B2 (en) 2005-04-28 2018-05-08 Proteus Digital Health, Inc. Communication system with enhanced partial power source and method of manufacturing same
US10610128B2 (en) 2005-04-28 2020-04-07 Proteus Digital Health, Inc. Pharma-informatics system
US8674825B2 (en) 2005-04-28 2014-03-18 Proteus Digital Health, Inc. Pharma-informatics system
US10542909B2 (en) 2005-04-28 2020-01-28 Proteus Digital Health, Inc. Communication system with partial power source
US10517507B2 (en) 2005-04-28 2019-12-31 Proteus Digital Health, Inc. Communication system with enhanced partial power source and method of manufacturing same
US8847766B2 (en) 2005-04-28 2014-09-30 Proteus Digital Health, Inc. Pharma-informatics system
US7978064B2 (en) 2005-04-28 2011-07-12 Proteus Biomedical, Inc. Communication system with partial power source
US9119554B2 (en) 2005-04-28 2015-09-01 Proteus Digital Health, Inc. Pharma-informatics system
US8816847B2 (en) 2005-04-28 2014-08-26 Proteus Digital Health, Inc. Communication system with partial power source
US8912908B2 (en) 2005-04-28 2014-12-16 Proteus Digital Health, Inc. Communication system with remote activation
US9198608B2 (en) 2005-04-28 2015-12-01 Proteus Digital Health, Inc. Communication system incorporated in a container
US8730031B2 (en) 2005-04-28 2014-05-20 Proteus Digital Health, Inc. Communication system using an implantable device
US9439582B2 (en) 2005-04-28 2016-09-13 Proteus Digital Health, Inc. Communication system with remote activation
US9681842B2 (en) 2005-04-28 2017-06-20 Proteus Digital Health, Inc. Pharma-informatics system
US9649066B2 (en) 2005-04-28 2017-05-16 Proteus Digital Health, Inc. Communication system with partial power source
US9597010B2 (en) 2005-04-28 2017-03-21 Proteus Digital Health, Inc. Communication system using an implantable device
US8802183B2 (en) 2005-04-28 2014-08-12 Proteus Digital Health, Inc. Communication system with enhanced partial power source and method of manufacturing same
US11476952B2 (en) 2005-04-28 2022-10-18 Otsuka Pharmaceutical Co., Ltd. Pharma-informatics system
US8547248B2 (en) 2005-09-01 2013-10-01 Proteus Digital Health, Inc. Implantable zero-wire communications system
US7571057B2 (en) * 2005-09-16 2009-08-04 General Electric Company System and method for monitoring degradation
US20070067114A1 (en) * 2005-09-16 2007-03-22 D Amato Fernando J System and method for monitoring degradation
US7990382B2 (en) 2006-01-03 2011-08-02 Masimo Corporation Virtual display
US20070191697A1 (en) * 2006-02-10 2007-08-16 Lynn Lawrence A System and method for SPO2 instability detection and quantification
US8728001B2 (en) 2006-02-10 2014-05-20 Lawrence A. Lynn Nasal capnographic pressure monitoring system
US8836513B2 (en) 2006-04-28 2014-09-16 Proteus Digital Health, Inc. Communication system incorporated in an ingestible product
US8956287B2 (en) 2006-05-02 2015-02-17 Proteus Digital Health, Inc. Patient customized therapeutic regimens
US11928614B2 (en) 2006-05-02 2024-03-12 Otsuka Pharmaceutical Co., Ltd. Patient customized therapeutic regimens
US10188348B2 (en) 2006-06-05 2019-01-29 Masimo Corporation Parameter upgrade system
US20070282478A1 (en) * 2006-06-05 2007-12-06 Ammar Al-Ali Parameter upgrade system
US11191485B2 (en) 2006-06-05 2021-12-07 Masimo Corporation Parameter upgrade system
US20080020037A1 (en) * 2006-07-11 2008-01-24 Robertson Timothy L Acoustic Pharma-Informatics System
US20080027568A1 (en) * 2006-07-27 2008-01-31 Scott Allan Pearson Method and Apparatus for Equipment Health Monitoring
US7536276B2 (en) * 2006-07-27 2009-05-19 Siemens Buildings Technologies, Inc. Method and apparatus for equipment health monitoring
US11857319B2 (en) 2006-10-12 2024-01-02 Masimo Corporation System and method for monitoring the life of a physiological sensor
US11317837B2 (en) 2006-10-12 2022-05-03 Masimo Corporation System and method for monitoring the life of a physiological sensor
US8054140B2 (en) 2006-10-17 2011-11-08 Proteus Biomedical, Inc. Low voltage oscillator for medical devices
US8945005B2 (en) 2006-10-25 2015-02-03 Proteus Digital Health, Inc. Controlled activation ingestible identifier
US11357730B2 (en) 2006-10-25 2022-06-14 Otsuka Pharmaceutical Co., Ltd. Controlled activation ingestible identifier
US10238604B2 (en) 2006-10-25 2019-03-26 Proteus Digital Health, Inc. Controlled activation ingestible identifier
US9444503B2 (en) 2006-11-20 2016-09-13 Proteus Digital Health, Inc. Active signal processing personal health signal receivers
US8718193B2 (en) 2006-11-20 2014-05-06 Proteus Digital Health, Inc. Active signal processing personal health signal receivers
US9083589B2 (en) 2006-11-20 2015-07-14 Proteus Digital Health, Inc. Active signal processing personal health signal receivers
US7395188B1 (en) 2006-12-07 2008-07-01 General Electric Company System and method for equipment life estimation
US7933754B2 (en) 2006-12-07 2011-04-26 General Electric Company System and method for damage propagation estimation
US20080140360A1 (en) * 2006-12-07 2008-06-12 General Electric Company System and method for damage propagation estimation
US20080140352A1 (en) * 2006-12-07 2008-06-12 General Electric Company System and method for equipment life estimation
US10441194B2 (en) 2007-02-01 2019-10-15 Proteus Digital Heal Th, Inc. Ingestible event marker systems
US8858432B2 (en) 2007-02-01 2014-10-14 Proteus Digital Health, Inc. Ingestible event marker systems
US11464423B2 (en) 2007-02-14 2022-10-11 Otsuka Pharmaceutical Co., Ltd. In-body power source having high surface area electrode
US8956288B2 (en) 2007-02-14 2015-02-17 Proteus Digital Health, Inc. In-body power source having high surface area electrode
US9270025B2 (en) 2007-03-09 2016-02-23 Proteus Digital Health, Inc. In-body device having deployable antenna
US8932221B2 (en) 2007-03-09 2015-01-13 Proteus Digital Health, Inc. In-body device having a multi-directional transmitter
US8115618B2 (en) 2007-05-24 2012-02-14 Proteus Biomedical, Inc. RFID antenna for in-body device
US10517506B2 (en) 2007-05-24 2019-12-31 Proteus Digital Health, Inc. Low profile antenna for in body device
US20080316020A1 (en) * 2007-05-24 2008-12-25 Robertson Timothy L Rfid antenna for in-body device
US8540632B2 (en) 2007-05-24 2013-09-24 Proteus Digital Health, Inc. Low profile antenna for in body device
US9433371B2 (en) 2007-09-25 2016-09-06 Proteus Digital Health, Inc. In-body device with virtual dipole signal amplification
US8961412B2 (en) 2007-09-25 2015-02-24 Proteus Digital Health, Inc. In-body device with virtual dipole signal amplification
US8274360B2 (en) 2007-10-12 2012-09-25 Masimo Corporation Systems and methods for storing, analyzing, and retrieving medical data
US9142117B2 (en) 2007-10-12 2015-09-22 Masimo Corporation Systems and methods for storing, analyzing, retrieving and displaying streaming medical data
US8810409B2 (en) 2008-03-05 2014-08-19 Proteus Digital Health, Inc. Multi-mode communication ingestible event markers and systems, and methods of using the same
US8258962B2 (en) 2008-03-05 2012-09-04 Proteus Biomedical, Inc. Multi-mode communication ingestible event markers and systems, and methods of using the same
US8542123B2 (en) 2008-03-05 2013-09-24 Proteus Digital Health, Inc. Multi-mode communication ingestible event markers and systems, and methods of using the same
US9258035B2 (en) 2008-03-05 2016-02-09 Proteus Digital Health, Inc. Multi-mode communication ingestible event markers and systems, and methods of using the same
US9060708B2 (en) 2008-03-05 2015-06-23 Proteus Digital Health, Inc. Multi-mode communication ingestible event markers and systems, and methods of using the same
US8352216B2 (en) * 2008-05-29 2013-01-08 General Electric Company System and method for advanced condition monitoring of an asset system
US20090299695A1 (en) * 2008-05-29 2009-12-03 General Electric Company System and method for advanced condition monitoring of an asset system
US10682071B2 (en) 2008-07-08 2020-06-16 Proteus Digital Health, Inc. State characterization based on multi-variate data fusion techniques
US9603550B2 (en) 2008-07-08 2017-03-28 Proteus Digital Health, Inc. State characterization based on multi-variate data fusion techniques
US11217342B2 (en) 2008-07-08 2022-01-04 Otsuka Pharmaceutical Co., Ltd. Ingestible event marker data framework
US9415010B2 (en) 2008-08-13 2016-08-16 Proteus Digital Health, Inc. Ingestible circuitry
US20100298668A1 (en) * 2008-08-13 2010-11-25 Hooman Hafezi Ingestible Circuitry
US8540633B2 (en) 2008-08-13 2013-09-24 Proteus Digital Health, Inc. Identifier circuits for generating unique identifiable indicators and techniques for producing same
US8721540B2 (en) 2008-08-13 2014-05-13 Proteus Digital Health, Inc. Ingestible circuitry
US20100082295A1 (en) * 2008-10-01 2010-04-01 Klaus Gram-Hansen Method and System of Wind Turbine Condition Monitoring
US8538729B2 (en) 2008-10-01 2013-09-17 Siemens Aktiengesellschaft Method and system of wind turbine condition monitoring
US8310336B2 (en) 2008-10-10 2012-11-13 Masimo Corporation Systems and methods for storing, analyzing, retrieving and displaying streaming medical data
US8036748B2 (en) 2008-11-13 2011-10-11 Proteus Biomedical, Inc. Ingestible therapy activator system and method
US8583227B2 (en) 2008-12-11 2013-11-12 Proteus Digital Health, Inc. Evaluation of gastrointestinal function using portable electroviscerography systems and methods of using the same
US8682616B2 (en) * 2008-12-15 2014-03-25 Snecma Identifying failures in an aeroengine
US9659423B2 (en) 2008-12-15 2017-05-23 Proteus Digital Health, Inc. Personal authentication apparatus system and method
US9439566B2 (en) 2008-12-15 2016-09-13 Proteus Digital Health, Inc. Re-wearable wireless device
US8545436B2 (en) 2008-12-15 2013-10-01 Proteus Digital Health, Inc. Body-associated receiver and method
US9149577B2 (en) 2008-12-15 2015-10-06 Proteus Digital Health, Inc. Body-associated receiver and method
US20110307220A1 (en) * 2008-12-15 2011-12-15 Snecma Identifying failures in an aeroengine
US8114021B2 (en) 2008-12-15 2012-02-14 Proteus Biomedical, Inc. Body-associated receiver and method
US9883819B2 (en) 2009-01-06 2018-02-06 Proteus Digital Health, Inc. Ingestion-related biofeedback and personalized medical therapy method and system
US8597186B2 (en) 2009-01-06 2013-12-03 Proteus Digital Health, Inc. Pharmaceutical dosages delivery system
US10007758B2 (en) 2009-03-04 2018-06-26 Masimo Corporation Medical monitoring system
US9218454B2 (en) 2009-03-04 2015-12-22 Masimo Corporation Medical monitoring system
US11087875B2 (en) 2009-03-04 2021-08-10 Masimo Corporation Medical monitoring system
US11145408B2 (en) 2009-03-04 2021-10-12 Masimo Corporation Medical communication protocol translator
US10366787B2 (en) 2009-03-04 2019-07-30 Masimo Corporation Physiological alarm threshold determination
US11133105B2 (en) 2009-03-04 2021-09-28 Masimo Corporation Medical monitoring system
US11158421B2 (en) 2009-03-04 2021-10-26 Masimo Corporation Physiological parameter alarm delay
US10032002B2 (en) 2009-03-04 2018-07-24 Masimo Corporation Medical monitoring system
US10255994B2 (en) 2009-03-04 2019-04-09 Masimo Corporation Physiological parameter alarm delay
US10325681B2 (en) 2009-03-04 2019-06-18 Masimo Corporation Physiological alarm threshold determination
US11923080B2 (en) 2009-03-04 2024-03-05 Masimo Corporation Medical monitoring system
US9119918B2 (en) 2009-03-25 2015-09-01 Proteus Digital Health, Inc. Probablistic pharmacokinetic and pharmacodynamic modeling
US8540664B2 (en) 2009-03-25 2013-09-24 Proteus Digital Health, Inc. Probablistic pharmacokinetic and pharmacodynamic modeling
US9320455B2 (en) 2009-04-28 2016-04-26 Proteus Digital Health, Inc. Highly reliable ingestible event markers and methods for using the same
US8545402B2 (en) 2009-04-28 2013-10-01 Proteus Digital Health, Inc. Highly reliable ingestible event markers and methods for using the same
US10588544B2 (en) 2009-04-28 2020-03-17 Proteus Digital Health, Inc. Highly reliable ingestible event markers and methods for using the same
US9149423B2 (en) 2009-05-12 2015-10-06 Proteus Digital Health, Inc. Ingestible event markers comprising an ingestible component
US11752262B2 (en) 2009-05-20 2023-09-12 Masimo Corporation Hemoglobin display and patient treatment
US10413666B2 (en) 2009-05-20 2019-09-17 Masimo Corporation Hemoglobin display and patient treatment
US9795739B2 (en) 2009-05-20 2017-10-24 Masimo Corporation Hemoglobin display and patient treatment
US10953156B2 (en) 2009-05-20 2021-03-23 Masimo Corporation Hemoglobin display and patient treatment
US8558563B2 (en) 2009-08-21 2013-10-15 Proteus Digital Health, Inc. Apparatus and method for measuring biochemical parameters
US8868453B2 (en) 2009-11-04 2014-10-21 Proteus Digital Health, Inc. System for supply chain management
US10305544B2 (en) 2009-11-04 2019-05-28 Proteus Digital Health, Inc. System for supply chain management
US9941931B2 (en) 2009-11-04 2018-04-10 Proteus Digital Health, Inc. System for supply chain management
US8784308B2 (en) 2009-12-02 2014-07-22 Proteus Digital Health, Inc. Integrated ingestible event marker system with pharmaceutical product
US9014779B2 (en) 2010-02-01 2015-04-21 Proteus Digital Health, Inc. Data gathering system
US10376218B2 (en) 2010-02-01 2019-08-13 Proteus Digital Health, Inc. Data gathering system
US10207093B2 (en) 2010-04-07 2019-02-19 Proteus Digital Health, Inc. Miniature ingestible device
US9597487B2 (en) 2010-04-07 2017-03-21 Proteus Digital Health, Inc. Miniature ingestible device
US11173290B2 (en) 2010-04-07 2021-11-16 Otsuka Pharmaceutical Co., Ltd. Miniature ingestible device
US10529044B2 (en) 2010-05-19 2020-01-07 Proteus Digital Health, Inc. Tracking and delivery confirmation of pharmaceutical products
US11504511B2 (en) 2010-11-22 2022-11-22 Otsuka Pharmaceutical Co., Ltd. Ingestible device with pharmaceutical product
US9107806B2 (en) 2010-11-22 2015-08-18 Proteus Digital Health, Inc. Ingestible device with pharmaceutical product
US9439599B2 (en) 2011-03-11 2016-09-13 Proteus Digital Health, Inc. Wearable personal body associated device with various physical configurations
US9032785B1 (en) 2011-07-01 2015-05-19 The United States Of America As Represented By The Administrator National Aeronautics And Space Administration Method for making measurements of the post-combustion residence time in a gas turbine engine
US11229378B2 (en) 2011-07-11 2022-01-25 Otsuka Pharmaceutical Co., Ltd. Communication system with enhanced partial power source and method of manufacturing same
US9756874B2 (en) 2011-07-11 2017-09-12 Proteus Digital Health, Inc. Masticable ingestible product and communication system therefor
US10223905B2 (en) 2011-07-21 2019-03-05 Proteus Digital Health, Inc. Mobile device and system for detection and communication of information received from an ingestible device
US9323894B2 (en) 2011-08-19 2016-04-26 Masimo Corporation Health care sanitation monitoring system
US11816973B2 (en) 2011-08-19 2023-11-14 Masimo Corporation Health care sanitation monitoring system
US11176801B2 (en) 2011-08-19 2021-11-16 Masimo Corporation Health care sanitation monitoring system
US9404895B2 (en) * 2011-10-20 2016-08-02 Nalco Company Method for early warning chatter detection and asset protection management
US20130103326A1 (en) * 2011-10-20 2013-04-25 William A. Von Drasek Method for early warning chatter detection and asset protection management
US10604896B2 (en) 2011-10-20 2020-03-31 Ecolab Usa Inc. Method for early warning chatter detection and asset protection management
US9235683B2 (en) 2011-11-09 2016-01-12 Proteus Digital Health, Inc. Apparatus, system, and method for managing adherence to a regimen
US9080925B2 (en) * 2012-06-13 2015-07-14 The Boeing Company Engine vibration and engine trim balance test system, apparatus and method
US20130338982A1 (en) * 2012-06-13 2013-12-19 Robert B. Schwab Engine Vibration And Engine Trim Balance Test System, Apparatus And Method
US9733141B1 (en) 2012-06-27 2017-08-15 The United States Of America As Represented By The Administrator Of National Aeronautics And Space Administration Method for making measurements of the post-combustion residence time in a gas turbine engine
US9271897B2 (en) 2012-07-23 2016-03-01 Proteus Digital Health, Inc. Techniques for manufacturing ingestible event markers comprising an ingestible component
US10642460B2 (en) 2012-10-05 2020-05-05 Cerner Innovation, Inc. Multi-action button for mobile devices
US10379713B2 (en) 2012-10-05 2019-08-13 Cerner Innovation, Inc. Multi-action button for mobile devices
US11232864B2 (en) 2012-10-05 2022-01-25 Cerner Innovation, Inc. Multi-action button for mobile devices
US11164673B2 (en) 2012-10-05 2021-11-02 Cerner Innovation, Inc. Attaching patient context to a call history associated with voice communication
US10978206B2 (en) 2012-10-05 2021-04-13 Cerner Innovation, Inc. Multi-action button for mobile devices
US9014918B2 (en) 2012-10-12 2015-04-21 Cummins Inc. Health monitoring systems and techniques for vehicle systems
US9268909B2 (en) 2012-10-18 2016-02-23 Proteus Digital Health, Inc. Apparatus, system, and method to adaptively optimize power dissipation and broadcast power in a power source for a communication device
US10777059B2 (en) 2012-12-31 2020-09-15 Cerner Innovation, Inc. Alert management utilizing mobile devices
US10580279B2 (en) 2012-12-31 2020-03-03 Cerner Innovation, Inc. Alert management utilizing mobile devices
US10275570B2 (en) 2012-12-31 2019-04-30 Cerner Innovation, Inc. Closed loop alert management
US11149123B2 (en) 2013-01-29 2021-10-19 Otsuka Pharmaceutical Co., Ltd. Highly-swellable polymeric films and compositions comprising the same
US11744481B2 (en) 2013-03-15 2023-09-05 Otsuka Pharmaceutical Co., Ltd. System, apparatus and methods for data collection and assessing outcomes
US10175376B2 (en) 2013-03-15 2019-01-08 Proteus Digital Health, Inc. Metal detector apparatus, system, and method
US11741771B2 (en) 2013-03-15 2023-08-29 Otsuka Pharmaceutical Co., Ltd. Personal authentication apparatus system and method
US11158149B2 (en) 2013-03-15 2021-10-26 Otsuka Pharmaceutical Co., Ltd. Personal authentication apparatus system and method
US10421658B2 (en) 2013-08-30 2019-09-24 Proteus Digital Health, Inc. Container with electronically controlled interlock
US9796576B2 (en) 2013-08-30 2017-10-24 Proteus Digital Health, Inc. Container with electronically controlled interlock
US11102038B2 (en) 2013-09-20 2021-08-24 Otsuka Pharmaceutical Co., Ltd. Methods, devices and systems for receiving and decoding a signal in the presence of noise using slices and warping
US10498572B2 (en) 2013-09-20 2019-12-03 Proteus Digital Health, Inc. Methods, devices and systems for receiving and decoding a signal in the presence of noise using slices and warping
US10097388B2 (en) 2013-09-20 2018-10-09 Proteus Digital Health, Inc. Methods, devices and systems for receiving and decoding a signal in the presence of noise using slices and warping
US9787511B2 (en) 2013-09-20 2017-10-10 Proteus Digital Health, Inc. Methods, devices and systems for receiving and decoding a signal in the presence of noise using slices and warping
US9270503B2 (en) 2013-09-20 2016-02-23 Proteus Digital Health, Inc. Methods, devices and systems for receiving and decoding a signal in the presence of noise using slices and warping
US9577864B2 (en) 2013-09-24 2017-02-21 Proteus Digital Health, Inc. Method and apparatus for use with received electromagnetic signal at a frequency not known exactly in advance
US10084880B2 (en) 2013-11-04 2018-09-25 Proteus Digital Health, Inc. Social media networking based on physiologic information
US10398161B2 (en) 2014-01-21 2019-09-03 Proteus Digital Heal Th, Inc. Masticable ingestible product and communication system therefor
US11051543B2 (en) 2015-07-21 2021-07-06 Otsuka Pharmaceutical Co. Ltd. Alginate on adhesive bilayer laminate film
US11749389B2 (en) 2015-10-06 2023-09-05 Cerner Innovation, Inc. Alert optimizer
US10607728B2 (en) 2015-10-06 2020-03-31 Cerner Innovation, Inc. Alert optimizer
US11342052B2 (en) 2015-10-06 2022-05-24 Cerner Innovation, Inc. Alert optimizer
US10697861B2 (en) * 2015-10-13 2020-06-30 Nec Corporation Structure abnormality detection device, structure abnormality detection method, storage medium, and structure abnormality detection system
US20180306677A1 (en) * 2015-10-13 2018-10-25 Nec Corporation Structure abnormality detection device, structure abnormality detection method, storage medium, and structure abnormality detection system
US10699812B2 (en) 2015-12-30 2020-06-30 Cerner Innovation, Inc. Intelligent alert suppression
US10388413B2 (en) 2015-12-30 2019-08-20 Cerner Innovation, Inc. Intelligent alert suppression
US11127498B2 (en) 2015-12-30 2021-09-21 Cerner Innovation, Inc. Intelligent alert suppression
US10797758B2 (en) 2016-07-22 2020-10-06 Proteus Digital Health, Inc. Electromagnetic sensing and detection of ingestible event markers
US10187121B2 (en) 2016-07-22 2019-01-22 Proteus Digital Health, Inc. Electromagnetic sensing and detection of ingestible event markers
US11529071B2 (en) 2016-10-26 2022-12-20 Otsuka Pharmaceutical Co., Ltd. Methods for manufacturing capsules with ingestible event markers
US11793419B2 (en) 2016-10-26 2023-10-24 Otsuka Pharmaceutical Co., Ltd. Methods for manufacturing capsules with ingestible event markers
US10941725B2 (en) 2017-06-27 2021-03-09 Rolls-Royce Corporation Vibration feedback controller
US10957445B2 (en) 2017-10-05 2021-03-23 Hill-Rom Services, Inc. Caregiver and staff information system
US11257588B2 (en) 2017-10-05 2022-02-22 Hill-Rom Services, Inc. Caregiver and staff information system
US11688511B2 (en) 2017-10-05 2023-06-27 Hill-Rom Services, Inc. Caregiver and staff information system
US11041271B2 (en) 2017-10-24 2021-06-22 Ecolab Usa Inc. Deposit detection in a paper making system via vibration analysis
US11727732B2 (en) 2019-09-27 2023-08-15 Ge Aviation Systems Limited Preserving vehicular raw vibration data for post-event analysis
US11455848B2 (en) 2019-09-27 2022-09-27 Ge Aviation Systems Limited Preserving vehicular raw vibration data for post-event analysis

Also Published As

Publication number Publication date
ATE441836T1 (de) 2009-09-15
ES2332874T3 (es) 2010-02-15
JP4859328B2 (ja) 2012-01-25
DK1297313T3 (da) 2009-12-14
US20020040278A1 (en) 2002-04-04
DE60139778D1 (de) 2009-10-15
AU2001267749A1 (en) 2002-01-14
JP2004502932A (ja) 2004-01-29
WO2002003041A1 (en) 2002-01-10
EP1297313A1 (de) 2003-04-02
GB0016561D0 (en) 2000-08-23
EP1297313B1 (de) 2009-09-02

Similar Documents

Publication Publication Date Title
US6928370B2 (en) Health monitoring
US6999884B2 (en) Bearing anomaly detection and location
US5210704A (en) System for prognosis and diagnostics of failure and wearout monitoring and for prediction of life expectancy of helicopter gearboxes and other rotating equipment
US7243048B2 (en) Fault detection system and method using multiway principal component analysis
US7571057B2 (en) System and method for monitoring degradation
US8484145B2 (en) Standardizing data used for monitoring an aeroengine
JP7340265B2 (ja) 異常検出装置、異常検出方法、およびプログラム
US11061390B2 (en) System fault isolation and ambiguity resolution
US20090326784A1 (en) Methods and Apparatuses For Monitoring A System
US8903692B2 (en) Method for the detection of failures in a turbomachine by means of a theoretical model of the thermodynamic cycle of the said turbomachine
De Francesco et al. A proposal to update LSA databases for an operational availability based on autonomic logistic
Ntantis et al. The impact of measurement noise in GPA diagnostic analysis of a gas turbine engine
CN113919207A (zh) 上面级开放式电气智能健康监测与管理系统
CA2598841A1 (en) State initialization for gas turbine engine performance diagnotics
Rabenoro et al. A methodology for the diagnostic of aircraft engine based on indicators aggregation
Zarate et al. Computation and monitoring of the deviations of gas turbine unmeasured parameters
Dewallef Application of the Kalman filter to health monitoring of gas turbine engines: A sequential approach to robust diagnosis
Li et al. Combining canonical variate analysis, probability approach and support vector regression for failure time prediction
Capata An artificial neural network-based diagnostic methodology for gas turbine path analysis—part II: case study
Chinakay et al. A PCA-based fault monitoring of splitter nozzles in gas turbine combustion chamber using exhaust gas temperature
Hickenbottom Proactive Approaches for Engine Health Management and a High Value Example
Babu et al. Framework for development of comprehensive diagnostic tool for fault detection and diagnosis of gas turbine engines
Przysowa et al. Health monitoring of turbomachinery based on blade tip-timing and tip-clearance
Fentaye et al. Sensor fault/failure correction and missing sensor replacement for enhanced real-time gas turbine diagnostics
Hansson Detection of Long Term Vibration Deviations in GasTurbine Monitoring Data

Legal Events

Date Code Title Description
AS Assignment

Owner name: ROLLS-ROYCE PLC, GREAT BRITAIN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:ANUZIS, PAUL;KING, STEVE P.;KING, DENNIS M.;AND OTHERS;REEL/FRAME:012294/0605;SIGNING DATES FROM 20010829 TO 20011005

AS Assignment

Owner name: OXFORD BIOSIGNALS LIMITED, ENGLAND

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:ROLLS-ROYCE PLC;REEL/FRAME:015078/0882

Effective date: 20031007

FEPP Fee payment procedure

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Free format text: PAYER NUMBER DE-ASSIGNED (ORIGINAL EVENT CODE: RMPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: OXFORD BIOSIGNALS LIMITED, UNITED KINGDOM

Free format text: CHANGE OF ADDRESS;ASSIGNOR:OXFORD BIOSIGNALS LIMITED;REEL/FRAME:016934/0867

Effective date: 20050304

FPAY Fee payment

Year of fee payment: 4

AS Assignment

Owner name: OPTIMIZED SYSTEMS AND SOLUTIONS LIMITED, UNITED KI

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:OXFORD BIOSIGNALS LIMITED;REEL/FRAME:024906/0209

Effective date: 20090925

FPAY Fee payment

Year of fee payment: 8

AS Assignment

Owner name: ROLLS-ROYCE CONTROLS AND DATA SERVICES LIMITED, GR

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:OPTIMIZED SYSTEMS AND SOLUTIONS LIMITED;REEL/FRAME:034601/0467

Effective date: 20140815

FPAY Fee payment

Year of fee payment: 12

AS Assignment

Owner name: ROLLS-ROYCE PLC, UNITED KINGDOM

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:ROLLS-ROYCE CONTROLS AND DATA SERVICES LIMITED;REEL/FRAME:043219/0929

Effective date: 20170523